Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4158 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.9059. Min Act: -0.1700
Data Index: 6393457 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.7497. Min Act: -0.1700
Data Index: 3514308 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.7184. Min Act: -0.1700
Data Index: 7324496 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.6872. Min Act: -0.1700
Data Index: 3308663 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.6872. Min Act: -0.1700
Data Index: 8753058 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.6872. Min Act: -0.1700
Data Index: 6689144 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.7184. Min Act: -0.1700
Data Index: 2301376 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.6872. Min Act: -0.1700
Data Index: 529639 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.6872. Min Act: -0.1700
Data Index: 96853 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.6247. Min Act: -0.1700
Data Index: 8562438 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.5934. Min Act: -0.1700
Data Index: 2464427 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.5622. Min Act: -0.1700
Data Index: 5919851 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.5309. Min Act: -0.1700
Data Index: 7030360 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.5309. Min Act: -0.1700
Data Index: 7957047 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.5309. Min Act: -0.1700
Data Index: 802672 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.4997. Min Act: -0.1700
Data Index: 43829 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.4684. Min Act: -0.1700
Data Index: 7345946 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.4372. Min Act: -0.1700
Data Index: 6983793 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.4684. Min Act: -0.1700
Data Index: 6445343 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9059. Min Range: -5.9059
Max Act: 5.4684. Min Act: -0.1700
Data Index: 737146 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19